Tested in Windows; In the Linux environment, it may be necessary to modify the image loading method to avoid the mismatch of input and reference（Thx 2665207323 ）.
torch = 1.13.0
Test Command: python lowlight_test.py (Chage the "filePath" and "filePath_high" to your own data path)
Train Command: python lowlight_train.py (Chage the "lowlight_images_path","highlight_images_path", "val_lowlight_images_path", and "val_highlight_images_path" to your own data path)
==================================================================================== new checkpoint in training：Looks like an interesting color change！！
<<==<<==<<==<<==<<==<<==<<==<<==<<==<<==<<==<<==<<==<<==<<==<<==<<==<<==<<==<<==<<==
